ANALISIS SENTIMEN TERHADAP FILM DIRTY VOTE BERDASARKAN OPINI PENGGUNA X (TWITTER) MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK

AINUR RAFIQ ABDILLAH, . (2024) ANALISIS SENTIMEN TERHADAP FILM DIRTY VOTE BERDASARKAN OPINI PENGGUNA X (TWITTER) MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK. Sarjana thesis, UNIVERSITAS NEGERI JAKARTA.

[img] Text
COVER.pdf

Download (3MB)
[img] Text
BAB 1.pdf

Download (317kB)
[img] Text
BAB 2.pdf
Restricted to Registered users only

Download (765kB) | Request a copy
[img] Text
BAB 3.pdf
Restricted to Registered users only

Download (394kB) | Request a copy
[img] Text
BAB 4.pdf
Restricted to Registered users only

Download (962kB) | Request a copy
[img] Text
BAB 5.pdf
Restricted to Registered users only

Download (299kB) | Request a copy
[img] Text
DAFTAR PUSTAKA.pdf

Download (299kB)
[img] Text
LAMPIRAN DAN RIWAYAT HIDUP.pdf
Restricted to Registered users only

Download (3MB) | Request a copy

Abstract

Penelitian ini berfokus pada Analisis Sentimen Terhadap Film Dirty Vote Berdasarkan Opini Pengguna X (Twitter) Menggunakan Metode Convolutional Neural Network (CNN), berdasarkan data tweet dari pengguna media sosial X (Twitter). Dalam penelitian ini, total data yang digunakan adalah 1010 tweet yang telah melalui proses pelabelan dan pre-processing dengan pembagian data latih dan data uji sebesar 80 : 20. Hasil dari penelitian ini menunjukkan bahwa terdapat nilai True Positive (TP) sebesar 44, True Negative (TN) sebesar 104, False Positive (FP) sebesar 26, False Negative (FN) sebesar 28. Nilai akurasi yang diperoleh adalah 73,27% dengan precision sebesar 80%, recall sebesar 78,8%, specificity sebesar 62,86% dan f1-score sebesar 79,4%. Analisis word cloud menunjukkan bahwa mayoritas opini terhadap film Dirty Vote cenderung positif, menandakan adanya dukungan atau apresiasi yang signifikan dari masyarakat. Berdasarkan hasil ini, disarankan untuk penelitian selanjutnya agar memperluas periode pengumpulan data, mengintegrasikan lebih banyak sumber data dari media sosial lain, serta membandingkan kinerja CNN dengan algoritma machine learning dan deep learning lainnya seperti KNN, SVM, Naïve Bayes, dan LSTM. Penyempurnaan pada tahap pre-processing juga direkomendasikan untuk meningkatkan akurasi model, terutama dalam mengatasi penggunaan bahasa gaul dan istilah slang word yang sering digunakan di media sosial. ****** This research focuses on Sentiment Analysis of Dirty Vote Movies Based on X User Opinions (Twitter) Using the Convolutional Neural Network (CNN) Method, based on tweet data from X social media users (Twitter). In this study, the total data used is 1010 tweets that have gone through the labeling and pre-processing process with the division of training data and test data by 80: The results of this study show that there are True Positive (TP) values of 44, True Negative (TN) of 104, False Positive (FP) of 26, False Negative (FN) of 28. The accuracy value obtained is 73.27% with a precision of 80%, recall of 78.8%, specificity of 62.86% and f1-score of 79.4%. Word cloud analysis shows that the majority of opinions on the Dirty Vote movie tend to be positive, indicating significant support or appreciation from the public. Based on these results, it is recommended for future research to expand the data collection period, integrate more data sources from other social media, and compare CNN performance with other machine learning and deep learning algorithms such as KNN, SVM, Naïve Bayes, and LSTM. Improvements in the pre-processing stage are also recommended to increase model accuracy, especially in overcoming the use of slang and slang words that are often used on social media.

Item Type: Thesis (Sarjana)
Additional Information: 1). Dr. Widodo, M.Kom. ; 2). Murien Nugraheni, S.T., M.C.
Subjects: Teknologi dan Ilmu Terapan > Teknik Komputer
Divisions: FT > S1 Pendidikan Teknik Informatika Komputer
Depositing User: Users 23365 not found.
Date Deposited: 25 Jul 2024 06:28
Last Modified: 25 Jul 2024 06:28
URI: http://repository.unj.ac.id/id/eprint/46272

Actions (login required)

View Item View Item